Python基础——Python与正则表达式

import re

re.match(pattern, string, flags=0)

result = re.match(r'hello', 'hello world')if result:    print("匹配成功:", result.group())  # hello

re.rearch(pattern, string, flags=0)

result = re.search(r'\d+', 'abc 123 def 456')    print("找到数字:", result.group())  # 123

line = "Cats are smarter than dogs"matchObj = re.match( r'dogs', line, re.M|re.I)if matchObj:   print ("match --> matchObj.group() : ", matchObj.group())else:   print ("No match!!")matchObj = re.search( r'dogs', line, re.M|re.I)if matchObj:   print ("search --> matchObj.group() : ", matchObj.group())else:   print ("No match!!")

No match!!search --> matchObj.group() :  dogs

re.compile(pattern[, flags])

pattern = re.compile(r'\d+')              m = pattern.match('11one12twothree34four')print(m)# 11

re.findall(pattern, string, flags=0)或pattern.findall(string[, pos[, endpos]])

numbers = re.findall(r'\d+', 'abc 123 def 456')print(numbers)  # ['123', '456']

re.finditer(pattern, string, flags=0)

for match in re.finditer(r'\d+', 'abc 123 def 456'):    print(match.group(), match.span())

re.sub(pattern, repl, string, count=0, flags=0)

text = "Python 2.7, Python 3.8"new_text = re.sub(r'\d\.\d', 'X.X', text)print(new_text)  # Python X.X, Python X.X

re.split(pattern, string[, maxsplit=0, flags=0])

parts = re.split(r'\s+', 'hello   world\tPython')print(parts)  # ['hello', 'world', 'Python']

text = "<div>content1</div><div>content2</div>"# 贪婪匹配 (默认)greedy = re.findall(r'<div>.*</div>', text)print("贪婪匹配:", greedy)  # 输出: ['<div>content1</div><div>content2</div>']# 非贪婪匹配non_greedy = re.findall(r'<div>.*?</div>', text)print("非贪婪匹配:", non_greedy)  # 输出: ['<div>content1</div>', '<div>content2</div>']

订单号: OD20240115001, 金额: ¥1,234.56, 客户: 张三订单号: OD20240116002, 金额: ¥890.00, 客户: 李四

订单号:\s*([^,]+),\s*金额:\s*¥([\d,.]+),\s*客户:\s*([\u4e00-\u9fa5]+)